{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unsupervised-grammar-induction-with-depth","title":"Unsupervised Grammar Induction with Depth-bounded PCFG","arxiv_id":"1802.08545","date":"2018-02-23","proceeding":"TACL 2018 1","authors":["Lifeng Jin","Finale Doshi-Velez","Timothy Miller","William Schuler","Lane Schwartz"],"abstract":"There has been recent interest in applying cognitively or empirically\nmotivated bounds on recursion depth to limit the search space of grammar\ninduction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al.,\n2016). This work extends this depth-bounding approach to probabilistic\ncontext-free grammar induction (DB-PCFG), which has a smaller parameter space\nthan hierarchical sequence models, and therefore more fully exploits the space\nreductions of depth-bounding. Results for this model on grammar acquisition\nfrom transcribed child-directed speech and newswire text exceed or are\ncompetitive with those of other models when evaluated on parse accuracy.\nMoreover, gram- mars acquired from this model demonstrate a consistent use of\ncategory labels, something which has not been demonstrated by other acquisition\nmodels.","url_abs":"http://arxiv.org/abs/1802.08545v2","url_pdf":"http://arxiv.org/pdf/1802.08545v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unsupervised-grammar-induction-with-depth","repo_url":"https://github.com/lifengjin/db-pcfg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.08545","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}